Towards integration of ontology and text-extracted data for event coreference reasoning

Recently, systems for automatic extraction of semantic information about events from large textual resources have been made available. These tools generate RDF datasets about the events described in the texts, enabling logical reasoning over the extracted information.. Ontological reasoning can be exploited to implement tasks that improve the quality of the extracted information, as, for example in event coreference (i.e., recognizing whether two textual descriptions refer to the same event). Starting from the observation that state of the art tools for event coreference do not exploit ontological information, in this paper, we propose a method to enrich event coreference detection on text-extracted event data by semantic-based rule reasoning.